© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59687
    Prev
    Next
    INDEX
    Explanations

    started as

    np_acts-logits-general · gemini-2.5-flash-lite

    genocide questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mno
    0.47
     postoje
    0.47
     اجتما
    0.46
     ν
    0.46
     handouts
    0.45
     amen
    0.44
     সভায়
    0.44
     convivial
    0.44
     houd
    0.44
    batross
    0.43
    POSITIVE LOGITS
    所以
    0.46
    started
    0.46
     ताकि
    0.44
     |--
    0.44
    Started
    0.44
     अभिक्रिया
    0.43
     started
    0.43
     elevate
    0.43
     所以
    0.43
    icent
    0.43
    Activations Density 0.000%

    No Known Activations